NLP Algorithm Engineer Intern

Location: APAC - Remote

Department: AI

Key Responsibilities

• LLM Application Development: Participate in the development of LLM-based applications, including Q&A systems, Agents, and algorithmic workflow systems.

• Workflow & Prompt Engineering: Assist in workflow development, as well as Prompt design and optimization to improve model performance.

• Agent Capabilities: Assist in implementing Tool Use (Function Calling) and foundational multi-turn dialogue logic.

• Core NLP Tasks: Implement tasks such as text classification, information extraction, and semantic matching.

• Model Modeling: Participate in small-scale modeling (classification/labeling tasks) and performance optimization.

• Data Management: Perform data cleaning, basic feature engineering, and result analysis.

Job Requirements

Basic Requirements

• Coding Proficiency: Proficient in Python with good coding habits and strong problem-solving skills.

• NLP Fundamentals: Familiar with common NLP tasks (Text Classification, NER, Semantic Matching, etc.) and their standard methodologies.

• Modeling Experience: Capable of independently completing the training and fine-tuning of simple classification or labeling models.

• Theoretical Knowledge: Deep understanding of Transformer / BERT principles (structure, training objectives, and application scenarios).

• LLM Exposure: Experience with Large Language Models (e.g., API calls, basic Prompt Engineering).

• Agent Concepts: Understanding of Agent fundamentals (e.g., Tool Use, multi-turn dialogue) or experience with basic implementations.

Preferred Qualifications (Plus)

• Practical Experience: Hands-on experience with Q&A systems (QA / Chatbot) or RAG (Retrieval-Augmented Generation) frameworks.

• ML/DL Foundations: Solid understanding of Machine Learning/Deep Learning (training workflows, loss functions, etc.).

• Software Engineering: Proficiency in Java or experience in backend development (API design and service implementation).

• Project Portfolio: Demonstrated experience through course projects, personal side projects, or open-source contributions.